Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Enable / Enables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     א
    0.36
     thậm
    0.36
    5
    0.36
     intelligents
    0.35
    <unused2119>
    0.35
     những
    0.35
     caches
    0.35
    个
    0.34
     (^
    0.34
     اندازه
    0.33
    POSITIVE LOGITS
    これを
    0.37
     nettoyage
    0.36
    予以
    0.35
    我要
    0.35
     Enabled
    0.35
    推动
    0.34
    ण्यास
    0.34
     vreau
    0.34
     Enable
    0.33
     Enables
    0.33
    Act Density 0.168%

    No Known Activations